ducha-aiki / Pytorch Sift
Licence: bsd-2-clause
PyTorch implementation of SIFT descriptor
Stars: ✭ 123
Projects that are alternatives of or similar to Pytorch Sift
Pytorch Learners Tutorial
PyTorch tutorial for learners
Stars: ✭ 97 (-21.14%)
Mutual labels: jupyter-notebook, cnn
End To End Sequence Labeling Via Bi Directional Lstm Cnns Crf Tutorial
Tutorial for End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF
Stars: ✭ 87 (-29.27%)
Mutual labels: jupyter-notebook, cnn
Gtsrb
Convolutional Neural Network for German Traffic Sign Recognition Benchmark
Stars: ✭ 65 (-47.15%)
Mutual labels: jupyter-notebook, cnn
Cnn Interpretability
🏥 Visualizing Convolutional Networks for MRI-based Diagnosis of Alzheimer’s Disease
Stars: ✭ 68 (-44.72%)
Mutual labels: jupyter-notebook, cnn
Pytorch Pos Tagging
A tutorial on how to implement models for part-of-speech tagging using PyTorch and TorchText.
Stars: ✭ 96 (-21.95%)
Mutual labels: jupyter-notebook, cnn
Convisualize nb
Visualisations for Convolutional Neural Networks in Pytorch
Stars: ✭ 57 (-53.66%)
Mutual labels: jupyter-notebook, cnn
Keras Oneclassanomalydetection
[5 FPS - 150 FPS] Learning Deep Features for One-Class Classification (AnomalyDetection). Corresponds RaspberryPi3. Convert to Tensorflow, ONNX, Caffe, PyTorch. Implementation by Python + OpenVINO/Tensorflow Lite.
Stars: ✭ 102 (-17.07%)
Mutual labels: jupyter-notebook, cnn
Codesearchnet
Datasets, tools, and benchmarks for representation learning of code.
Stars: ✭ 1,378 (+1020.33%)
Mutual labels: jupyter-notebook, cnn
Deeplearning Nlp Models
A small, interpretable codebase containing the re-implementation of a few "deep" NLP models in PyTorch. Colab notebooks to run with GPUs. Models: word2vec, CNNs, transformer, gpt.
Stars: ✭ 64 (-47.97%)
Mutual labels: jupyter-notebook, cnn
Deeplearning tutorials
The deeplearning algorithms implemented by tensorflow
Stars: ✭ 1,580 (+1184.55%)
Mutual labels: jupyter-notebook, cnn
Embedded gcnn
Embedded Graph Convolutional Neural Networks (EGCNN) in TensorFlow
Stars: ✭ 60 (-51.22%)
Mutual labels: jupyter-notebook, cnn
Understaing Datasets Estimators Tfrecords
Try to use tf.estimator and tf.data together to train a cnn model.
Stars: ✭ 76 (-38.21%)
Mutual labels: jupyter-notebook, cnn
One Pixel Attack Keras
Keras implementation of "One pixel attack for fooling deep neural networks" using differential evolution on Cifar10 and ImageNet
Stars: ✭ 1,097 (+791.87%)
Mutual labels: jupyter-notebook, cnn
Cnn intent classification
CNN for intent classification task in a Chatbot
Stars: ✭ 90 (-26.83%)
Mutual labels: jupyter-notebook, cnn
Lung Diseases Classifier
Diseases Detection from NIH Chest X-ray data
Stars: ✭ 52 (-57.72%)
Mutual labels: jupyter-notebook, cnn
Text nn
Text classification models. Used a submodule for other projects.
Stars: ✭ 55 (-55.28%)
Mutual labels: jupyter-notebook, cnn
Facedetector
A re-implementation of mtcnn. Joint training, tutorial and deployment together.
Stars: ✭ 99 (-19.51%)
Mutual labels: jupyter-notebook, cnn
Self Driving Car
A End to End CNN Model which predicts the steering wheel angle based on the video/image
Stars: ✭ 106 (-13.82%)
Mutual labels: jupyter-notebook, cnn
This is an differentiable pytorch implementation of SIFT patch descriptor. It is very slow for describing one patch, but quite fast for batch. It can be used for descriptop-based learning shape of affine feature.
UPD 08/2019 : pytorch-sift is added to kornia and available by kornia.features.SIFTDescriptor
There are different implementations of the SIFT on the web. I tried to match Michal Perdoch implementation, which gives high quality features for image retrieval CVPR2009. However, on planar datasets, it is inferior to vlfeat implementation. The main difference is gaussian weighting window parameters, so I have made a vlfeat-like version too. MP version weights patch center much more (see image below, left) and additionally crops everything outside the circular region. Right is vlfeat version
descriptor_mp_mode = SIFTNet(patch_size = 65,
sigma_type= 'hesamp',
masktype='CircularGauss')
descriptor_vlfeat_mode = SIFTNet(patch_size = 65,
sigma_type= 'vlfeat',
masktype='Gauss')
Results:
OPENCV-SIFT - mAP
Easy Hard Tough mean
------- ------- --------- -------
0.47788 0.20997 0.0967711 0.26154
VLFeat-SIFT - mAP
Easy Hard Tough mean
-------- -------- --------- --------
0.466584 0.203966 0.0935743 0.254708
PYTORCH-SIFT-VLFEAT-65 - mAP
Easy Hard Tough mean
-------- -------- --------- --------
0.472563 0.202458 0.0910371 0.255353
NUMPY-SIFT-VLFEAT-65 - mAP
Easy Hard Tough mean
-------- -------- --------- --------
0.449431 0.197918 0.0905395 0.245963
PYTORCH-SIFT-MP-65 - mAP
Easy Hard Tough mean
-------- -------- --------- --------
0.430887 0.184834 0.0832707 0.232997
NUMPY-SIFT-MP-65 - mAP
Easy Hard Tough mean
-------- ------- --------- --------
0.417296 0.18114 0.0820582 0.226832
Speed:
- 0.00246 s per 65x65 patch - numpy SIFT
- 0.00028 s per 65x65 patch - C++ SIFT
- 0.00074 s per 65x65 patch - CPU, 256 patches per batch
- 0.00038 s per 65x65 patch - GPU (GM940, mobile), 256 patches per batch
- 0.00038 s per 65x65 patch - GPU (GM940, mobile), 256 patches per batch
If you use this code for academic purposes, please cite the following paper:
@InProceedings{AffNet2018,
title = {Repeatability Is Not Enough: Learning Affine Regions via Discriminability},
author = {Dmytro Mishkin, Filip Radenovic, Jiri Matas},
booktitle = {Proceedings of ECCV},
year = 2018,
month = sep
}
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].